End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

Machine Learning library for the web and Node.

Deal with bad samples in your dataset dynamically, use Transforms as Filters, and more!

A day to day plan for this challenge. Covers both theoritical and practical aspects

Deep learning GUI frame work for enterprise

A simpler way of reading and augmenting image segmentation data into TensorFlow

SEGAN pytorch implementation https://arxiv.org/abs/1703.09452

Social Media Mining Toolkit (SMMT) main repository

sciblox - Easier Data Science and Machine Learning

I will update this repository to learn Machine learning with python with statistics content and materials

“Data science” is just about as broad of a term as they come. It may be easiest to describe what it is by listing its more concrete components: Data exploration & analysis. Included here: Pandas; NumPy; SciPy; a helping hand from Python's Standard Library.

DTCleaner: data cleaning using multi-target decision trees.

Data Science and Machine learning in JavaScript

Flow-based data pre-processing for deep learning

Demo on the capability of Yandex CatBoost gradient boosting classifier on a fictitious IBM HR dataset obtained from Kaggle. Data exploration, cleaning, preprocessing and model tuning are performed on the dataset

Data preparation for data science projects.

Pipeline module for parallel real-time data processing for machine learning models development and production purposes.

A lightweight data processing framework for Apache Spark

A comprehensive approach for stock trading implemented using Neural Network and Reinforcement Learning separately.

A command-line utility program for automating the trivial, frequently occurring data preparation tasks: missing value interpolation, outlier removal, and encoding categorical variables.

Datasets and Codes for the ML Series

My MSc on Data Science final project. This is a library for Data Pre-processing Algorithms for Streaming in Flink (DPASF)

Extract mfcc vectors and phones from TIMIT dataset

This is a project based on Data Science Bowl 2017. I did my best to propose a solution for the problem but I am still new to Deep Learning so my solution is not the optimal one but it can definitely be improved with some fine tuning and better resources.

A command line tool for preprocessing, manipulating and serializing font files for deep learning applications.

Aim is to come up with a job recommender system, which takes the skills from LinkedIn and jobs from Indeed and throws the best jobs available for you according to your skills.

Implementation scripts of Machine Learning algorithms on Scikit-learn and Keras for complete novice..

Academic project for Advances in Data Science and Architecture course

A Deep Learning Model for detecting Malware Applications

SAU Makine Öğrenmesi Eğitim İçerikleri